I am Gautam Singh, a Ph.D. graduate in Computer Science from George Mason University. My advisor is Prof. Jana Kosecka. My research interests are in the areas of computer vision, machine learning and robotics with an application to scene understanding from images and/or videos. Specifically, my work applies these interests to problems like semantic parsing of scenes, content-based image retrieval and location recognition.

Before coming to George Mason, I completed my Bachelors with Honors in Computer Science and Engineering from IIIT, Hyderabad, India in 2007. I worked with Prof. Kamal Karlapalem on outlier detection using frequent itemset mining for my undergraduate thesis.


Publications

Visual Scene Understanding through Semantic Segmentation [PDF | TALK]
Gautam Singh
Ph.D. Thesis, Department of Computer Science, George Mason University

Introspective Semantic Segmentation [PDF]
Gautam Singh and Jana Kosecka
Scene Understanding Workshop (SUNw) (in conjunction with CVPR 2014)

Introspective Semantic Segmentation [PDF | POSTER]
Gautam Singh and Jana Kosecka
IEEE Winter Conference on Applications of Computer Vision (WACV 2014)

Semantic Context for Nonparametric Scene Parsing and Scene Classification [PDF]
Gautam Singh and Jana Kosecka
Scene Understanding Workshop (SUNw) (in conjunction with CVPR 2013)

Nonparametric Scene Parsing with Adaptive Feature Relevance and Semantic Context [PDF | SPOTLIGHT (jump to 10:08) | POSTER]
Gautam Singh and Jana Kosecka
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2013)

Localization in Urban Environments Using a Panoramic Gist Descriptor [PDF]
Ana C. Murillo, Gautam Singh, Jana Kosecka, and J. J. Guerrero
IEEE Transactions on Robotics (IEEE-TRO)

Acquiring Semantics Induced Topology in Urban Environments [PDF | TALK]
Gautam Singh and Jana Kosecka
IEEE International Conference on Robotics and Automation (ICRA 2012)

Semantic parsing of street scenes from video [PDF]
Branislav Micusik, Jana Kosecka and Gautam Singh
International Journal of Robotics Research (IJRR)

Recognizing Manipulation Actions in Arts and Crafts Shows using Domain Specific Visual and Textual Cues [PDF]
Ben Sapp, Rizwan Chaudhry, Xiaodong Yu, Gautam Singh, Ian Perera, Francis Ferraro, Evelyne Tzoukermann, Jana Kosecka and Jan Neumann
International Workshop on Video Event Categorization, Tagging and Retrieval for Real-World Applications (VECTaR2011) (in conjunction with ICCV 2011)

Language Models for Semantic Extraction and Filtering in Video Action Recognition [PDF]
Evelyne Tzoukermann, Jan Neumann, Jana Kosecka, Cornelia Fermuller, Ian Perera, Frank Ferraro, Ben Sapp, Rizwan Chaudhry and Gautam Singh
International Workshop on Language-Action Tools for Cognitive Artificial Agents (AAAI-11 Workshop) (in conjunction with AAAI 2011)

Localizing Objects and Actions in Videos Using Accompanying Text [PDF available on request]
Jan Neumann, Cornelia Fermuller, Jana Kosecka, Evelyne Tzoukermann, Rizwan Chaudhry, Francis Ferrero, He He, Yi Li, Ian Perera, Ben Sapp, Gautam Singh, Ching Lik Teo and Xiaodong Yu
Technical report for CLSP JHU Summer Workshop, 2010 (WS'10)

Visual Loop Closing using Gist Descriptors in Manhattan World [PDF]
Gautam Singh and Jana Kosecka
Workshop on Omnidirectional Robot Vision (OmniRoboVis2010) (in conjunction with ICRA 2010)